© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94197
    Prev
    Next
    INDEX
    Explanations

    vaso

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BarStyle
    -0.59
    BeginContext
    -0.57
    Lähteet
    -0.57
    Jereo
    -0.56
     getApp
    -0.55
     ſeveral
    -0.54
    úrate
    -0.53
    gery
    -0.53
     uVar
    -0.52
    tacular
    -0.52
    POSITIVE LOGITS
    OGND
    0.58
    出版年
    0.55
     سكانية
    0.49
    δι
    0.47
     iprot
    0.47
     =======
    0.47
     Exacts
    0.46
    const
    0.46
    Demografie
    0.46
     Mox
    0.46
    Activations Density 0.008%

    No Known Activations